Young-Dong Yu

Young-Dong Yu

Auto-generated profile, based on publicly available information

Young-Dong Yu

Department of Surgery Division of HBP Surgery Korea University College of Medicine Seoul Korea

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 September 2021 in International Journal of Surgery
Verified
Journal Article
Closed access
Kwang-sig LeeKwang-sig Lee
Kwang-sig Lee
JJJin-Young Jang
Jin-Young Jang
YYYoung-Dong Yu
Young-Dong Yu
JHJin Seok Heo
Jin Seok Heo
HHHo-Seong Han
Ho-Seong Han
SKSunghwa Kang
Sunghwa Kang
Or Purpose: Pancreatic ductal adenocarcinoma (PDAC) is a leading cause of mortality in the world with the overall 5-year survival rate of 6%. The survival of patients with PDAC is closely related to recurrence and therefore it is necessary to identify the risk factors for recurrence. This study uses artificial intelligence approaches and multi-center registry data to analyze the recurrence of pancreatic cancer after surgery and its major determinants. Data came from 4846 patients enrolled in a multi-center registry system, the Korea Tumor Registry System (KOTUS). The random forest and the Cox proportional-hazards model (the Cox model) were applied and compared for the prediction of disease-free survival. Variable importance, the contribution of a variable for the performance of the model, was used for identifying major predictors of disease-free survival after surgery. The C-Index was introduced as a criterion for validating the models trained. Based on variable importance from the random forest, major predictors of disease-free survival after surgery were tumor size (0.00310), tumor grade (0.00211), TNM stage (0.00211), T stage (0.00146) and lymphovascular invasion (0.00125). The coefficients of these variables were statistically significant in the Cox model (p < 0.05). The C-Index averages of the random forest and the Cox model were 0.6805 and 0.7738, respectively. This is the first artificial-intelligence study with multi-center registry data to predict disease-free survival after the surgery of pancreatic cancer. The findings of this methodological study demonstrate that artificial intelligence can provide a valuable decision-support system for treating patients undergoing surgery for pancreatic cancer. However, at present, further studies are needed to demonstrate the actual benefit of applying machine learning algorithms in clinical practice.

1 September 2022 in International Journal of Surgery
Verified
Journal Article
Closed access
YYYoung-Dong Yu
Young-Dong Yu
Kwang-sig LeeKwang-sig Lee
Kwang-sig Lee
JKJong Man Kim
Jong Man Kim
JRJe Ho Ryu
Je Ho Ryu
JLJae-Geun Lee
Jae-Geun Lee
DKDong-Sik Kim
Dong-Sik Kim
Previous studies have indicated that the model for end-stage liver disease (MELD) score may fail to predict post-transplantation patient survival. Similarly, other scores (donor MELD score, balance of risk score) that have been developed to predict transplant outcomes have not gained widespread use. These scores are typically derived using linear statistical models. This study aimed to compare the performance of traditional statistical models with machine learning approaches for predicting survival following liver transplantation. Data were obtained from 785 deceased donor liver transplant recipients enrolled in the Korean Organ Transplant Registry (2014-2019). Five machine learning methods (random forest, artificial neural networks, decision tree, naïve Bayes, and support vector machine) and four traditional statistical models (Cox regression, MELD score, donor MELD score and balance of risk score) were compared to predict survival. Among the machine learning methods, the random forest yielded the highest area under the receiver operating characteristic curve (AUC-ROC) values (1-month = 0.80; 3-month = 0.85; and 12-month = 0.81) for predicting survival. The AUC-ROC values of the Cox regression analysis were 0.75, 0.86, and 0.77 for 1-month, 3-month, and 12-month post-transplant survival, respectively. However, the AUC-ROC values of the MELD, donor MELD, and balance of risk scores were all below 0.70. Based on the variable importance of the random forest analysis in this study, the major predictors associated with survival were cold ischemia time, donor ICU stay, recipient weight, recipient BMI, recipient age, recipient INR, and recipient albumin level. As with the Cox regression analysis, donor ICU stay, donor bilirubin level, BAR score, and recipient albumin levels were also important factors associated with post-transplant survival in the RF model. The coefficients of these variables were also statistically significant in the Cox model (p < 0.05). The SHAP ranges for selected predictors for the 12-month survival were (-0.02,0.10) for recipient albumin, (-0.05,0.07) for donor bilirubin and (-0.02,0.25) for recipient height. Surprisingly, although not statistically significant in the Cox model, recipient weight, recipient BMI, recipient age, or recipient INR were important factors in our random forest model for predicting post-transplantation survival. Machine learning algorithms such as the random forest were superior to conventional Cox regression and previously reported survival scores for predicting 1-month, 3-month, and 12-month survival following liver transplantation. Therefore, artificial intelligence may have significant potential in aiding clinical decision-making during liver transplantation, including matching donors and recipients.

10 June 2023 in Scientific Reports
Verified
Journal Article
Open access
PDF file
YCYoo Jin Choi
Yoo Jin Choi
NSNguyen Thanh Sang
Nguyen Thanh Sang
HJHye-Sung Jo
Hye-Sung Jo
DKDong-Sik Kim
Dong-Sik Kim
YYYoung-Dong Yu
Young-Dong Yu
Minimally invasive surgery is usually more beneficial than open surgeries in various fields of surgery. With the newly developed Single-Port (SP) robotic surgical system, even single-site surgery has become easier to access. We compared single-incision robotic cholecystectomy between the Si/Xi and SP systems. This retrospective single-center study enrolled patients who underwent single-incision robotic cholecystectomy between July 2014 and July 2021. The clinical outcomes of the da Vinci Si/Xi and SP systems were compared. In total, 334 patients underwent single-incision robotic cholecystectomy (118 Si/Xi vs. 216 SP). The SP group had more chronic or acute cholecystitis than the Si/Xi group did. There was more bile spillage in the Si/Xi group during the surgery. The total operative and docking times were significantly shorter in the SP group. There was no difference in the postoperative outcomes. The SP system is safe and feasible regarding comparable postoperative complication rates and is more convenient regarding docking and techniques.

14 March 2022 in Langenbeck's Archives of Surgery
Verified
Journal Article
Closed access
PDF file
YCYoo Jin Choi
Yoo Jin Choi
HJHye-Sung Jo
Hye-Sung Jo
DKDong-Sik Kim
Dong-Sik Kim
YYYoung-Dong Yu
Young-Dong Yu

4 January 2020 in World Journal of Surgical Oncology
Verified
Journal Article
Open access
PDF file
HJHye-Sung Jo
Hye-Sung Jo
DKDong-Sik Kim
Dong-Sik Kim
YYYoung-Dong Yu
Young-Dong Yu
WKWoo-Hyoung Kang
Woo-Hyoung Kang
KYKyung Chul Yoon
Kyung Chul Yoon
Background: Radical resection is the only curative treatment for patients with hilar cholangiocarcinoma. While left-side hepatectomy (LH) may have an oncological disadvantage over right-side hepatectomy (RH) owing to the contiguous anatomical relationship between right hepatic inflow and biliary confluence, a small future liver remnant after RH could cause worse surgical morbidity and mortality. We retrospectively compared surgical morbidity and long-term outcome between RH and LH to determine the optimal surgical strategy for the treatment of hilar cholangiocarcinoma. Methods: This study considered 83 patients who underwent surgical resection for hilar cholangiocarcinoma between 2010 and 2017. Among them, 57 patients undergoing curative-intent surgery including liver resection were enrolled for analysis—33 in the RH group and 27 in the LH group. Prospectively collected clinicopathologic characteristics, perioperative outcomes, and long-term survival were evaluated. Results: Portal vein embolization was more frequently performed in the RH group than in the LH group (18.2% vs. 0%, P = 0.034). The proportion of R0 resection was comparable in both groups (75.8% vs. 75.0%, P = 0.948). The 5-year overall and recurrence-free survival rates did not differ between the groups (37.7% vs. 41.9%, P = 0.500, and 26.3% vs. 33.9%, P = 0.580, respectively). The side of liver resection did not affect long-term survival. In multivariate analysis, transfusion (odds ratio, 3.12 [1.42–6.87], P = 0.005) and post-hepatectomy liver failure (≥ grade B, 4.62 [1.86–11.49], P = 0.001) were independent risk factors for overall survival. Conclusions: We recommend deciding the side of liver resection according to the possibility of achieving radical resection considering the anatomical differences between RH and LH.

1 October 2022 in International Journal of Surgery
Verified
Journal Article
Closed access
HJHye-Sung Jo
Hye-Sung Jo
YYYoung-Dong Yu
Young-Dong Yu
YCYoo Jin Choi
Yoo Jin Choi
DKDong-Sik Kim
Dong-Sik Kim
Adult-to-adult living donor liver transplantation (LDLT) is a notable type of liver transplantation. Several centers prefer the right liver graft (RLG) over the left liver graft (LLG) for better recovery of recipients. We compared the outcomes of donors and recipients between LDLT using LLGs and RLGs. The study cohort comprised of 25 patients in the LLG group and 93 in the RLG group. When both hemiliver grafts met the selection criteria, an LLG was preferred. When portal flow (≥300 ml/min/100gLW) and hepatic venous pressure gradient (≥10 mmHg) were increased, intraoperative splenic artery ligation was performed for portal modulation. Postoperatively, somatostatin was administered when small-for-size syndrome (SFSS) was highly suspected. The graft-to-recipient weight ratio was lower in the LLG group than in the RLG group. There was no significant complication above Clavien-Dindo grade IIIA in donors. Regarding recipient outcomes, SFSS occurred in four (16.0%) patients in the LLG group and three (3.2%) in the RLG group (P = 0.036). Splenic artery ligation was frequently performed in the LLG group than the RLG group (5 [20.0%] vs. 12 [12.9%], P = 0.035) and 5 patients received intravenous continuous somatostatin for 7 (5-12) days. SFSS-related hospital mortality did not occur. There was no significant difference in the short-term and long-term outcomes between the groups. This study demonstrates the comparable outcomes of donors and recipients between the LLG and RLG groups although with a higher risk of SFSS that needs high experience to avoid severe complications and graft loss. We expect LLG to be used more actively in adult-to-adult LDLT with portal flow modulation strategies to overcome fatal SFSS.